Download presentation
Presentation is loading. Please wait.
Published byPolly Kelley Modified over 8 years ago
1
Understanding Business Intelligence with Neural Networks James McCaffrey Microsoft Research Labs Wednesday, May 4, 2016 3:15 – 4:00 PM Room Breakers CD
2
Agenda and Goals What is a neural network? How do neural networks work? How can you create a neural network? Q & A
3
training data independent variables / predictors / signals / attributes / features / X-values “the thing to classify (predict)” / label / dependent variable / Y What is a Neural Network?
4
How Do Neural Networks Work? 35 49,000 M 3.5 4.9 0.0 1.0 0.23 0.15 Republican 0.62 inputhiddenoutput High weights and biases
5
How Do Neural Networks Work? 35 49,000 M 3.5 4.9 0.0 1.0 0.23 0.15 Republican 0.62 inputhiddenoutput High encoding normalization weights and biases
6
Under the Hood 0.10 0.30 0.20 ?? 1). (0.1)(4.0) + (0.2)(-5.0) + (0.3)(6.0) = 1.2 2). 1.2 + 2.0 = 3.2 3). Activation(3.2) = 0.73 4). ?? = Local output = 0.73 1.0 perceptron weights and biases activation function
7
Activation Functions and Why You Don’t Care Logistic Sigmoid Output between [0, 1] y = 1.0 / (1.0 + e –x ) Hyperbolic Tangent Output between [-1, +1] y = tanh(x) = (e x – e -x ) / (e x + e -x ) Softmax Outputs between [0, 1] and sum to 1.0 y = (e -xi ) / Σ ( e -xj ) activation function
8
Training and Free Parameters – No Free Lunch Number of weights and bias values to determine: (n i * n h ) + (n h * n o ) + (n h + n o ) Ex: n i = 10, n h = 20, n o = 3 (10 * 20) + (20 * 3) + (20 + 3) = 283 back-propagation free parameters
9
Research vs. Reality back-propagation free parameters
10
Over-Fitting: The Biggest Challenge over-fitting error, accuracy
11
Four Ways to Actually Create a Neural Network Use an existing application tool (Weka, Azure ML) Hire a vendor company Use a library/API to create a custom system Create custom system from scratch
12
Weka
13
Azure Machine Learning
14
Neural Network from Scratch
16
Summary If your data can be put into a spreadsheet, then a neural network can be used to predict any of the columns. You don’t need to know how to implement a neural network, but you do need to know the 10 key vocabulary terms so you can communicate. The 10 Key Terms: perceptron, features, encoding, normalization, weights & biases, activation function, back-propagation, free parameters, over-fitting, error & accuracy. Neural network tools for Big Data are not quite ready for prime time.
17
Resources WEKA Step-by-Step: https://jamesmccaffrey.wordpress.com/2015/07/16/neural-networks-with-weka-quick-start-tutorial/ Technical Bible: ftp://ftp.sas.com/pub/neural/FAQ.html Python Implementation: http://www.quaetrix.com/NeuralNetwork/neuralnet.py
18
Thank You! Understanding Business Intelligence with Neural Networks James McCaffrey Microsoft Research Labs Wednesday, May 4, 2016 3:15 – 4:00 PM Room Breakers CD
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.